Real-Time Safe Control of Neural Network Dynamic Models with Sound Approximation

arXiv:2404.13456v1 Announce Type: new
Abstract: Safe control of neural network dynamic models (NNDMs) is important to robotics and many applications. However, it remains challenging to compute an optimal safe control in real time for NNDM. To enable real-time computation, we propose to use a sound approximation of the NNDM in the control synthesis. In particular, we propose Bernstein over-approximated neural dynamics (BOND) based on the Bernstein polynomial over-approximation (BPO) of ReLU activation functions in NNDM. To mitigate the errors introduced …

abstract applications approximation arxiv computation compute control cs.lg cs.ro cs.sy dynamic eess.sy however network neural network real-time robotics safe sound type